Week 6

Combining DataFrames

From the course website:

import pandas as pd
import numpy as np

rng = np.random.default_rng(10)

names = ["Ava", "Benjamin", "Charlotte", "Daniel", "Emma", "Fredric", "Gianna"]
courses = ["MTH 141", "MTH 142", "MTH 241", "MTH 306", "MTH 309", "MTH 311"]
rooms = ["NSC 216", "Capen 110", "Park 440"]

# concat rows data
scores1 = rng.integers(0, 100, 12).reshape(4, 3)
scores2 = rng.integers(0, 100, 9).reshape(3, 3)
columns = ["problem_1", "problem_2", "problem_3"]
sec1 = pd.DataFrame(scores1, index=names[:4], columns=columns)
sec2 = pd.DataFrame(scores2, index=names[4:7], columns=columns)

# concat columns data
scores1 = rng.integers(0, 100, 8).reshape(4, 2)
scores2 = rng.integers(0, 100, 9).reshape(3, 3)
part1 = pd.DataFrame(scores1,
                     index=names[:4],
                     columns=["problem_1", "problem_2"])
part2 = pd.DataFrame(scores2,
                     index=names[:3],
                     columns=["problem_3", "problem_4", "problem_5"])

# merging data
office_nums = rng.integers(100, 150, len(names[:-1]))
courses = pd.DataFrame({"course": courses,
                        "instructor": rng.choice(names[1:], len(courses))})
instructors = pd.DataFrame({"name": names[:-1], "office": office_nums}, dtype="object")

Concatenating along rows

display(sec1)
display(sec2)

	problem_1	problem_2	problem_3
Ava	77	95	26
Benjamin	20	79	82
Charlotte	51	14	83
Daniel	51	15	13

	problem_1	problem_2	problem_3
Emma	41	68	40
Fredric	84	0	42
Gianna	52	95	23

pd.concat([sec1, sec2])

	problem_1	problem_2	problem_3
Ava	77	95	26
Benjamin	20	79	82
Charlotte	51	14	83
Daniel	51	15	13
Emma	41	68	40
Fredric	84	0	42
Gianna	52	95	23

df = pd.concat([sec1, sec2], keys=["section_1", "section_2"])
df

		problem_1	problem_2	problem_3
section_1	Ava	77	95	26
	Benjamin	20	79	82
	Charlotte	51	14	83
	Daniel	51	15	13
section_2	Emma	41	68	40
	Fredric	84	0	42
	Gianna	52	95	23

df.loc["section_2"]

	problem_1	problem_2	problem_3
Emma	41	68	40
Fredric	84	0	42
Gianna	52	95	23

df.loc[("section_2", "Gianna")]

problem_1    52
problem_2    95
problem_3    23
Name: (section_2, Gianna), dtype: int64

sec1 = sec1.rename({"problem_3": "problem_3a"}, axis=1)
sec1

	problem_1	problem_2	problem_3a
Ava	77	95	26
Benjamin	20	79	82
Charlotte	51	14	83
Daniel	51	15	13

sec2 = sec2.rename({"problem_3": "problem_3b"}, axis=1)
sec2

	problem_1	problem_2	problem_3b
Emma	41	68	40
Fredric	84	0	42
Gianna	52	95	23

pd.concat([sec1, sec2])

	problem_1	problem_2	problem_3a	problem_3b
Ava	77	95	26.0	NaN
Benjamin	20	79	82.0	NaN
Charlotte	51	14	83.0	NaN
Daniel	51	15	13.0	NaN
Emma	41	68	NaN	40.0
Fredric	84	0	NaN	42.0
Gianna	52	95	NaN	23.0

pd.concat([sec1, sec2], join="inner")

	problem_1	problem_2
Ava	77	95
Benjamin	20	79
Charlotte	51	14
Daniel	51	15
Emma	41	68
Fredric	84	0
Gianna	52	95

Concatenating along columns

display(part1)
display(part2)

	problem_1	problem_2
Ava	82	7
Benjamin	33	74
Charlotte	57	93
Daniel	75	91

	problem_3	problem_4	problem_5
Ava	82	13	93
Benjamin	84	14	97
Charlotte	74	31	13

pd.concat([part1, part2], axis=1)

	problem_1	problem_2	problem_3	problem_4	problem_5
Ava	82	7	82.0	13.0	93.0
Benjamin	33	74	84.0	14.0	97.0
Charlotte	57	93	74.0	31.0	13.0
Daniel	75	91	NaN	NaN	NaN

Merging

display(courses)
display(instructors)

	course	instructor
0	MTH 141	Emma
1	MTH 142	Charlotte
2	MTH 241	Benjamin
3	MTH 306	Gianna
4	MTH 309	Charlotte
5	MTH 311	Emma

	name	office
0	Ava	119
1	Benjamin	145
2	Charlotte	139
3	Daniel	111
4	Emma	124
5	Fredric	142

schedule = pd.merge(courses, instructors, left_on="instructor", right_on="name", how="inner")
schedule

	course	instructor	name	office
0	MTH 141	Emma	Emma	124
1	MTH 311	Emma	Emma	124
2	MTH 142	Charlotte	Charlotte	139
3	MTH 309	Charlotte	Charlotte	139
4	MTH 241	Benjamin	Benjamin	145

schedule.drop("name", axis=1)

	course	instructor	office
0	MTH 141	Emma	124
1	MTH 311	Emma	124
2	MTH 142	Charlotte	139
3	MTH 309	Charlotte	139
4	MTH 241	Benjamin	145

pd.merge(courses, instructors, left_on="instructor", right_on="name", how="left")

	course	instructor	name	office
0	MTH 141	Emma	Emma	124
1	MTH 142	Charlotte	Charlotte	139
2	MTH 241	Benjamin	Benjamin	145
3	MTH 306	Gianna	NaN	NaN
4	MTH 309	Charlotte	Charlotte	139
5	MTH 311	Emma	Emma	124

pd.merge(courses, instructors, left_on="instructor", right_on="name", how="right")

	course	instructor	name	office
0	NaN	NaN	Ava	119
1	MTH 241	Benjamin	Benjamin	145
2	MTH 142	Charlotte	Charlotte	139
3	MTH 309	Charlotte	Charlotte	139
4	NaN	NaN	Daniel	111
5	MTH 141	Emma	Emma	124
6	MTH 311	Emma	Emma	124
7	NaN	NaN	Fredric	142

pd.merge(courses, instructors, left_on="instructor", right_on="name", how="outer")

	course	instructor	name	office
0	MTH 141	Emma	Emma	124
1	MTH 311	Emma	Emma	124
2	MTH 142	Charlotte	Charlotte	139
3	MTH 309	Charlotte	Charlotte	139
4	MTH 241	Benjamin	Benjamin	145
5	MTH 306	Gianna	NaN	NaN
6	NaN	NaN	Ava	119
7	NaN	NaN	Daniel	111
8	NaN	NaN	Fredric	142

Baby names project

from zipfile import ZipFile

with ZipFile("names.zip", 'r') as z:
    z.extractall(path="baby_names")
    
df = pd.read_csv("baby_names/yob1880.txt", names=["name", "sex", "count"])
df

	name	sex	count
0	Mary	F	7065
1	Anna	F	2604
2	Emma	F	2003
3	Elizabeth	F	1939
4	Minnie	F	1746
...	...	...	...
1995	Woodie	M	5
1996	Worthy	M	5
1997	Wright	M	5
1998	York	M	5
1999	Zachariah	M	5

2000 rows × 3 columns

import glob
file_names = glob.glob("baby_names/yob*.txt")
file_names

['baby_names/yob2000.txt',
 'baby_names/yob2014.txt',
 'baby_names/yob1938.txt',
 'baby_names/yob1910.txt',
 'baby_names/yob1904.txt',
 'baby_names/yob1905.txt',
 'baby_names/yob1911.txt',
 'baby_names/yob1939.txt',
 'baby_names/yob2015.txt',
 'baby_names/yob2001.txt',
 'baby_names/yob2017.txt',
 'baby_names/yob2003.txt',
 'baby_names/yob1907.txt',
 'baby_names/yob1913.txt',
 'baby_names/yob1898.txt',
 'baby_names/yob1899.txt',
 'baby_names/yob1912.txt',
 'baby_names/yob1906.txt',
 'baby_names/yob2002.txt',
 'baby_names/yob2016.txt',
 'baby_names/yob2012.txt',
 'baby_names/yob2006.txt',
 'baby_names/yob1902.txt',
 'baby_names/yob1916.txt',
 'baby_names/yob1889.txt',
 'baby_names/yob1888.txt',
 'baby_names/yob1917.txt',
 'baby_names/yob1903.txt',
 'baby_names/yob2007.txt',
 'baby_names/yob2013.txt',
 'baby_names/yob2005.txt',
 'baby_names/yob2011.txt',
 'baby_names/yob1915.txt',
 'baby_names/yob1901.txt',
 'baby_names/yob1929.txt',
 'baby_names/yob1928.txt',
 'baby_names/yob1900.txt',
 'baby_names/yob1914.txt',
 'baby_names/yob2010.txt',
 'baby_names/yob2004.txt',
 'baby_names/yob1973.txt',
 'baby_names/yob1967.txt',
 'baby_names/yob1998.txt',
 'baby_names/yob1999.txt',
 'baby_names/yob1966.txt',
 'baby_names/yob1972.txt',
 'baby_names/yob1958.txt',
 'baby_names/yob1964.txt',
 'baby_names/yob1970.txt',
 'baby_names/yob1971.txt',
 'baby_names/yob1965.txt',
 'baby_names/yob1959.txt',
 'baby_names/yob1961.txt',
 'baby_names/yob1975.txt',
 'baby_names/yob1949.txt',
 'baby_names/yob1948.txt',
 'baby_names/yob1974.txt',
 'baby_names/yob1960.txt',
 'baby_names/yob1976.txt',
 'baby_names/yob1962.txt',
 'baby_names/yob1989.txt',
 'baby_names/yob1988.txt',
 'baby_names/yob1963.txt',
 'baby_names/yob1977.txt',
 'baby_names/yob1952.txt',
 'baby_names/yob1946.txt',
 'baby_names/yob1991.txt',
 'baby_names/yob1985.txt',
 'baby_names/yob1984.txt',
 'baby_names/yob1990.txt',
 'baby_names/yob1947.txt',
 'baby_names/yob1953.txt',
 'baby_names/yob1979.txt',
 'baby_names/yob1945.txt',
 'baby_names/yob1951.txt',
 'baby_names/yob1986.txt',
 'baby_names/yob1992.txt',
 'baby_names/yob1993.txt',
 'baby_names/yob1987.txt',
 'baby_names/yob1950.txt',
 'baby_names/yob1944.txt',
 'baby_names/yob1978.txt',
 'baby_names/yob1940.txt',
 'baby_names/yob1954.txt',
 'baby_names/yob1968.txt',
 'baby_names/yob1983.txt',
 'baby_names/yob1997.txt',
 'baby_names/yob1996.txt',
 'baby_names/yob1982.txt',
 'baby_names/yob1969.txt',
 'baby_names/yob1955.txt',
 'baby_names/yob1941.txt',
 'baby_names/yob1957.txt',
 'baby_names/yob1943.txt',
 'baby_names/yob1994.txt',
 'baby_names/yob1980.txt',
 'baby_names/yob1981.txt',
 'baby_names/yob1995.txt',
 'baby_names/yob1942.txt',
 'baby_names/yob1956.txt',
 'baby_names/yob2009.txt',
 'baby_names/yob1919.txt',
 'baby_names/yob1931.txt',
 'baby_names/yob1925.txt',
 'baby_names/yob1886.txt',
 'baby_names/yob1892.txt',
 'baby_names/yob1893.txt',
 'baby_names/yob1887.txt',
 'baby_names/yob1924.txt',
 'baby_names/yob1930.txt',
 'baby_names/yob1918.txt',
 'baby_names/yob2020.txt',
 'baby_names/yob2008.txt',
 'baby_names/yob1926.txt',
 'baby_names/yob1932.txt',
 'baby_names/yob1891.txt',
 'baby_names/yob1885.txt',
 'baby_names/yob1884.txt',
 'baby_names/yob1890.txt',
 'baby_names/yob1933.txt',
 'baby_names/yob1927.txt',
 'baby_names/yob1923.txt',
 'baby_names/yob1937.txt',
 'baby_names/yob1894.txt',
 'baby_names/yob1880.txt',
 'baby_names/yob1881.txt',
 'baby_names/yob1895.txt',
 'baby_names/yob1936.txt',
 'baby_names/yob1922.txt',
 'baby_names/yob2018.txt',
 'baby_names/yob1934.txt',
 'baby_names/yob1920.txt',
 'baby_names/yob1908.txt',
 'baby_names/yob1883.txt',
 'baby_names/yob1897.txt',
 'baby_names/yob1896.txt',
 'baby_names/yob1882.txt',
 'baby_names/yob1909.txt',
 'baby_names/yob1921.txt',
 'baby_names/yob1935.txt',
 'baby_names/yob2019.txt']

frames = [pd.read_csv(f, names=["name", "sex", "count"]) for f in file_names]
df = pd.concat(frames)

df

	name	sex	count
0	Emily	F	25957
1	Hannah	F	23084
2	Madison	F	19968
3	Ashley	F	17997
4	Sarah	F	17706
...	...	...	...
32025	Zyheem	M	5
32026	Zykel	M	5
32027	Zyking	M	5
32028	Zyn	M	5
32029	Zyran	M	5

2020863 rows × 3 columns

df[df["name"] == "Emily"]

	name	sex	count
0	Emily	F	25957
20595	Emily	M	30
6	Emily	F	12652
26398	Emily	M	11
163	Emily	F	1308
...	...	...	...
120	Emily	F	2184
9881	Emily	M	6
172	Emily	F	1094
11	Emily	F	8229
27045	Emily	M	8

218 rows × 3 columns

f = file_names[0]
f

'baby_names/yob2000.txt'

"hello.there".split('.')[0]

'hello'

int(f.split(".")[0][-4:])

2000

years = [int(f.split(".")[0][-4:]) for f in file_names]
years

[2000,
 2014,
 1938,
 1910,
 1904,
 1905,
 1911,
 1939,
 2015,
 2001,
 2017,
 2003,
 1907,
 1913,
 1898,
 1899,
 1912,
 1906,
 2002,
 2016,
 2012,
 2006,
 1902,
 1916,
 1889,
 1888,
 1917,
 1903,
 2007,
 2013,
 2005,
 2011,
 1915,
 1901,
 1929,
 1928,
 1900,
 1914,
 2010,
 2004,
 1973,
 1967,
 1998,
 1999,
 1966,
 1972,
 1958,
 1964,
 1970,
 1971,
 1965,
 1959,
 1961,
 1975,
 1949,
 1948,
 1974,
 1960,
 1976,
 1962,
 1989,
 1988,
 1963,
 1977,
 1952,
 1946,
 1991,
 1985,
 1984,
 1990,
 1947,
 1953,
 1979,
 1945,
 1951,
 1986,
 1992,
 1993,
 1987,
 1950,
 1944,
 1978,
 1940,
 1954,
 1968,
 1983,
 1997,
 1996,
 1982,
 1969,
 1955,
 1941,
 1957,
 1943,
 1994,
 1980,
 1981,
 1995,
 1942,
 1956,
 2009,
 1919,
 1931,
 1925,
 1886,
 1892,
 1893,
 1887,
 1924,
 1930,
 1918,
 2020,
 2008,
 1926,
 1932,
 1891,
 1885,
 1884,
 1890,
 1933,
 1927,
 1923,
 1937,
 1894,
 1880,
 1881,
 1895,
 1936,
 1922,
 2018,
 1934,
 1920,
 1908,
 1883,
 1897,
 1896,
 1882,
 1909,
 1921,
 1935,
 2019]

df = pd.concat(frames, keys=years)
df

		name	sex	count
2000	0	Emily	F	25957
	1	Hannah	F	23084
	2	Madison	F	19968
	3	Ashley	F	17997
	4	Sarah	F	17706
...	...	...	...	...
2019	32025	Zyheem	M	5
	32026	Zykel	M	5
	32027	Zyking	M	5
	32028	Zyn	M	5
	32029	Zyran	M	5

2020863 rows × 3 columns

df.loc[1880]

	name	sex	count
0	Mary	F	7065
1	Anna	F	2604
2	Emma	F	2003
3	Elizabeth	F	1939
4	Minnie	F	1746
...	...	...	...
1995	Woodie	M	5
1996	Worthy	M	5
1997	Wright	M	5
1998	York	M	5
1999	Zachariah	M	5

2000 rows × 3 columns

df.loc[2020]

	name	sex	count
0	Olivia	F	17535
1	Emma	F	15581
2	Ava	F	13084
3	Charlotte	F	13003
4	Sophia	F	12976
...	...	...	...
31266	Zykell	M	5
31267	Zylus	M	5
31268	Zymari	M	5
31269	Zyn	M	5
31270	Zyran	M	5

31271 rows × 3 columns

df = df.reset_index(level=0)
df

	level_0	name	sex	count
0	2000	Emily	F	25957
1	2000	Hannah	F	23084
2	2000	Madison	F	19968
3	2000	Ashley	F	17997
4	2000	Sarah	F	17706
...	...	...	...	...
32025	2019	Zyheem	M	5
32026	2019	Zykel	M	5
32027	2019	Zyking	M	5
32028	2019	Zyn	M	5
32029	2019	Zyran	M	5

2020863 rows × 4 columns

df = df.rename({"level_0": "year"}, axis=1)
df

	year	name	sex	count
0	2000	Emily	F	25957
1	2000	Hannah	F	23084
2	2000	Madison	F	19968
3	2000	Ashley	F	17997
4	2000	Sarah	F	17706
...	...	...	...	...
32025	2019	Zyheem	M	5
32026	2019	Zykel	M	5
32027	2019	Zyking	M	5
32028	2019	Zyn	M	5
32029	2019	Zyran	M	5

2020863 rows × 4 columns

df = df.sort_values(by=["year"])
df

	year	name	sex	count
1638	1880	Dayton	M	8
1341	1880	Vern	M	19
1340	1880	Stewart	M	19
1339	1880	Randolph	M	19
1338	1880	Lucien	M	19
...	...	...	...	...
20853	2020	Hisham	M	31
20854	2020	Jahleel	M	31
20855	2020	Jameir	M	31
20857	2020	Jenesis	M	31
4287	2020	Medina	F	32

2020863 rows × 4 columns

df.to_csv("baby_names.csv", index=False)

pd.read_csv("baby_names.csv")

	year	name	sex	count
0	1880	Dayton	M	8
1	1880	Vern	M	19
2	1880	Stewart	M	19
3	1880	Randolph	M	19
4	1880	Lucien	M	19
...	...	...	...	...
2020858	2020	Hisham	M	31
2020859	2020	Jahleel	M	31
2020860	2020	Jameir	M	31
2020861	2020	Jenesis	M	31
2020862	2020	Medina	F	32

2020863 rows × 4 columns

Exercises

Seaborn

%config InlineBackend.figure_format = 'retina'
import seaborn as sns
import matplotlib.pyplot as plt

tips = sns.load_dataset("tips")
tips.head()

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4

plt.scatter(tips["total_bill"], tips["tip"]);

With seaborn:

sns.relplot(data=tips,
            x="total_bill",
            y="tip"
           );

Setting themes:

sns.set_theme(style="darkgrid", # darkgrid, whitegrid, dark, white, ticks
              palette="colorblind",  # deep, muted, pastel, bright, dark, colorblind
              font_scale=1.3
             )

sns.relplot(data=tips,
            x="total_bill",
            y="tip"
           );

with sns.axes_style("whitegrid"):
    sns.relplot(data=tips,
            x="total_bill",
            y="tip"
           );

Controlling size:

sns.relplot(data=tips,
            x="total_bill",
            y="tip",
            height=6,
            aspect=2
           );

sns.relplot(data=tips,
            x="total_bill",
            y="tip",
            hue="day",
            height=6,
            aspect=2
           );

sns.relplot(data=tips,
            x="total_bill",
            y="tip",
            hue="day",
            size="size",
            sizes=(5,400),
            height=6,
            aspect=2
           );

sns.relplot(data=tips,
            x="total_bill",
            y="tip",
            hue="day",
            size="size",
            sizes=(5,400),
            col="time",
            height=6,
            aspect=1
           );

sns.relplot(data=tips,
            x="total_bill",
            y="tip",
            hue="day",
            size="size",
            sizes=(5,400),
            col="time",
            row="sex",
            height=6,
            aspect=1,
           );

Figure-level and axes-level functions

g = sns.jointplot(data=tips, x="total_bill", y="tip", height=8)
g.set_axis_labels("Total bill", "Tip")
g.fig.suptitle('Restaurant data', y = 1.01);

plt.figure(figsize=(14,5))

plt.subplot(121)
sns.scatterplot(data=tips, 
                x="total_bill",
                y="tip",
                hue="day",
               );
plt.xlabel('Total bill')
plt.ylabel('Tip')
plt.title('Restaurant data')
plt.plot([0,50], [0, 10], 'r-', lw=5)

plt.subplot(122)
plt.plot([1, 2, 3, 4], [3, 0, 2, 1], 'bo-');

Plotly Express

import plotly.io as pio
pio.renderers.default = "notebook"

import plotly.express as px

fig = px.scatter(data_frame=tips, 
                 x="total_bill",
                 y="tip",
                 title="Restaurant data",
                 width=800,
                 height=400
                )
fig.show()

fig = px.scatter(data_frame=tips, 
                 x="total_bill",
                 y="tip",
                 color="day",
                 title = "Restaurant data"
                )
fig.show()

fig = px.scatter(data_frame=tips, 
                 x="total_bill",
                 y="tip",
                 color="day",
                 size="size",
                 title = "Restaurant data"
                )
fig.show()

fig = px.scatter(data_frame=tips, 
                 x="total_bill",
                 y="tip",
                 color="day",
                 size="size",
                 facet_col="time",
                 title = "Restaurant data"
                )
fig.show()

fig = px.scatter(data_frame=tips, 
                 x="total_bill",
                 y="tip",
                 color="day",
                 size="size",
                 facet_col="time",
                 facet_row="sex",
                 title = "Restaurant data"
                )
fig.show()

fig.write_html("my_plot.html")

Plot types

Line plot

gapminder = px.data.gapminder()
gapminder.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

ac = gapminder[gapminder["country"].str[0] == "A"]
ac.head()

	country	continent	year	lifeExp	pop	gdpPercap	iso_alpha	iso_num
0	Afghanistan	Asia	1952	28.801	8425333	779.445314	AFG	4
1	Afghanistan	Asia	1957	30.332	9240934	820.853030	AFG	4
2	Afghanistan	Asia	1962	31.997	10267083	853.100710	AFG	4
3	Afghanistan	Asia	1967	34.020	11537966	836.197138	AFG	4
4	Afghanistan	Asia	1972	36.088	13079460	739.981106	AFG	4

fig = px.line(ac,
              x="year",
              y="gdpPercap",
              color="country",
              hover_name="country",
              labels={"year" : "Year", # change x-axis label
                        "gdpPercap" : "GDP per capita",  # change y-axis label
                        "country" : "Country name"},  # change legend title
              title="Line plot"
             )
fig.show()

Bar plot

tips

	total_bill	tip	sex	smoker	day	time	size
0	16.99	1.01	Female	No	Sun	Dinner	2
1	10.34	1.66	Male	No	Sun	Dinner	3
2	21.01	3.50	Male	No	Sun	Dinner	3
3	23.68	3.31	Male	No	Sun	Dinner	2
4	24.59	3.61	Female	No	Sun	Dinner	4
...	...	...	...	...	...	...	...
239	29.03	5.92	Male	No	Sat	Dinner	3
240	27.18	2.00	Female	Yes	Sat	Dinner	2
241	22.67	2.00	Male	Yes	Sat	Dinner	2
242	17.82	1.75	Male	No	Sat	Dinner	2
243	18.78	3.00	Female	No	Thur	Dinner	2

244 rows × 7 columns

fig = px.bar(tips,
             x="day",
             y="tip",
             color="sex",
             barmode="group", # relative group overlay
             category_orders = {"day" : ["Thur", "Fri", "Sat", "Sun"]}, # order days on x-axis
             title="Bar plot"
            )
fig.show()

# DataFrame with total tip amounts for a given day and sex
t = tips.groupby(["day", "sex"])["tip"].sum().reset_index()
display(t.head())

	day	sex	tip
0	Thur	Male	89.41
1	Thur	Female	82.42
2	Fri	Male	26.93
3	Fri	Female	25.03
4	Sat	Male	181.95

fig = px.bar(t,
             x="day",
             y="tip",
             color="sex",
             barmode="group", # relative group overlay
             category_orders = {"day" : ["Thur", "Fri", "Sat", "Sun"]}, # order days on x-axis
             title="Bar plot"
            )
fig.show()

Strip plot

fig = px.strip(tips,
               x="day",
               y="tip",
               color="sex",
               category_orders = {"day" : ["Thur", "Fri", "Sat", "Sun"]}, # order days on x-axis
               title = "Strip plot"
              )
fig.show()

Box plot

fig = px.box(tips,
             x="day",
             y="total_bill",
             color="sex",
             labels = {"total_bill" : "total bill"}, 
             category_orders = {"day" : ["Thur", "Fri", "Sat", "Sun"]},
             title="Box plot")
fig.show()

Histogram

fig = px.histogram(tips,
                   x="total_bill",
                   labels = {"total_bill" : "total bill"},
                   nbins = 6,
                   #histnorm = "percent",  # probability, percent, probability density
                   title = "Histogram"
                  )

fig.update_layout({"bargap": 0.02})  # add space between bars

fig.show()

scatter_3d

fig = px.scatter_3d(data_frame=tips,
                 x = "total_bill",
                 y = "tip", 
                 z = "size",
                 color = "day"
                )
fig.show()

Choropleth maps

From the course website:

url = "https://raw.githubusercontent.com/plotly/datasets/master/2011_us_ag_exports.csv"

import pandas as pd

df = pd.read_csv(url)
df.head(5)

	code	state	category	total exports	beef	pork	poultry	dairy	fruits fresh	fruits proc	total fruits	veggies fresh	veggies proc	total veggies	corn	wheat	cotton
0	AL	Alabama	state	1390.63	34.4	10.6	481.0	4.06	8.0	17.1	25.11	5.5	8.9	14.33	34.9	70.0	317.61
1	AK	Alaska	state	13.31	0.2	0.1	0.0	0.19	0.0	0.0	0.00	0.6	1.0	1.56	0.0	0.0	0.00
2	AZ	Arizona	state	1463.17	71.3	17.9	0.0	105.48	19.3	41.0	60.27	147.5	239.4	386.91	7.3	48.7	423.95
3	AR	Arkansas	state	3586.02	53.2	29.4	562.9	3.53	2.2	4.7	6.88	4.4	7.1	11.45	69.5	114.5	665.44
4	CA	California	state	16472.88	228.7	11.1	225.4	929.95	2791.8	5944.6	8736.40	803.2	1303.5	2106.79	34.6	249.3	1064.95

df["exports_cotton"] = df["cotton"] > 0
df.head()

	code	state	category	total exports	beef	pork	poultry	dairy	fruits fresh	fruits proc	total fruits	veggies fresh	veggies proc	total veggies	corn	wheat	cotton	exports_cotton
0	AL	Alabama	state	1390.63	34.4	10.6	481.0	4.06	8.0	17.1	25.11	5.5	8.9	14.33	34.9	70.0	317.61	True
1	AK	Alaska	state	13.31	0.2	0.1	0.0	0.19	0.0	0.0	0.00	0.6	1.0	1.56	0.0	0.0	0.00	False
2	AZ	Arizona	state	1463.17	71.3	17.9	0.0	105.48	19.3	41.0	60.27	147.5	239.4	386.91	7.3	48.7	423.95	True
3	AR	Arkansas	state	3586.02	53.2	29.4	562.9	3.53	2.2	4.7	6.88	4.4	7.1	11.45	69.5	114.5	665.44	True
4	CA	California	state	16472.88	228.7	11.1	225.4	929.95	2791.8	5944.6	8736.40	803.2	1303.5	2106.79	34.6	249.3	1064.95	True

import plotly.express as px
fig = px.choropleth(df, 
                    locationmode="USA-states", 
                    locations="code", 
                    color="exports_cotton",
                    scope="usa",
                    color_discrete_sequence = ["red", "lightgray"],
                    title = "States exporting cotton",
                    hover_name = "state",
                    hover_data={"exports_cotton": False, "code":False}
                   )

fig.update_layout(showlegend=False)
fig.show()

df["veggies_perc"] = (df["total veggies"]/df["total exports"])*100
df.head(5)

	code	state	category	total exports	beef	pork	poultry	dairy	fruits fresh	fruits proc	total fruits	veggies fresh	veggies proc	total veggies	corn	wheat	cotton	exports_cotton	veggies_perc
0	AL	Alabama	state	1390.63	34.4	10.6	481.0	4.06	8.0	17.1	25.11	5.5	8.9	14.33	34.9	70.0	317.61	True	1.030468
1	AK	Alaska	state	13.31	0.2	0.1	0.0	0.19	0.0	0.0	0.00	0.6	1.0	1.56	0.0	0.0	0.00	False	11.720511
2	AZ	Arizona	state	1463.17	71.3	17.9	0.0	105.48	19.3	41.0	60.27	147.5	239.4	386.91	7.3	48.7	423.95	True	26.443270
3	AR	Arkansas	state	3586.02	53.2	29.4	562.9	3.53	2.2	4.7	6.88	4.4	7.1	11.45	69.5	114.5	665.44	True	0.319295
4	CA	California	state	16472.88	228.7	11.1	225.4	929.95	2791.8	5944.6	8736.40	803.2	1303.5	2106.79	34.6	249.3	1064.95	True	12.789445

fig = px.choropleth(df,
                    locationmode="USA-states",
                    scope="usa",
                    locations="code",
                    color="veggies_perc",
                    hover_name="state",
                    hover_data={"veggies_perc": ':.2f', "code": False},
                    labels = {"veggies_perc": "veggies %"},
                    color_continuous_scale= px.colors.sequential.tempo, #px.colors.sequential.Reds_r,
                    title="Percentage of vegetables in agricultural exports",
                   )

fig.update_traces(marker_line_color='white', 
                  hovertemplate = '<b>%{hovertext}</b><br>Veggies exports: %{z:.2f}%<extra></extra>'
                 )
    
fig.show()

fig.data[0].hovertemplate

'<b>%{hovertext}</b><br>Veggies exports: %{z:.2f}%<extra></extra>'

dir(px.colors.sequential)

['Aggrnyl',
 'Aggrnyl_r',
 'Agsunset',
 'Agsunset_r',
 'Blackbody',
 'Blackbody_r',
 'Bluered',
 'Bluered_r',
 'Blues',
 'Blues_r',
 'Blugrn',
 'Blugrn_r',
 'Bluyl',
 'Bluyl_r',
 'Brwnyl',
 'Brwnyl_r',
 'BuGn',
 'BuGn_r',
 'BuPu',
 'BuPu_r',
 'Burg',
 'Burg_r',
 'Burgyl',
 'Burgyl_r',
 'Cividis',
 'Cividis_r',
 'Darkmint',
 'Darkmint_r',
 'Electric',
 'Electric_r',
 'Emrld',
 'Emrld_r',
 'GnBu',
 'GnBu_r',
 'Greens',
 'Greens_r',
 'Greys',
 'Greys_r',
 'Hot',
 'Hot_r',
 'Inferno',
 'Inferno_r',
 'Jet',
 'Jet_r',
 'Magenta',
 'Magenta_r',
 'Magma',
 'Magma_r',
 'Mint',
 'Mint_r',
 'OrRd',
 'OrRd_r',
 'Oranges',
 'Oranges_r',
 'Oryel',
 'Oryel_r',
 'Peach',
 'Peach_r',
 'Pinkyl',
 'Pinkyl_r',
 'Plasma',
 'Plasma_r',
 'Plotly3',
 'Plotly3_r',
 'PuBu',
 'PuBuGn',
 'PuBuGn_r',
 'PuBu_r',
 'PuRd',
 'PuRd_r',
 'Purp',
 'Purp_r',
 'Purples',
 'Purples_r',
 'Purpor',
 'Purpor_r',
 'Rainbow',
 'Rainbow_r',
 'RdBu',
 'RdBu_r',
 'RdPu',
 'RdPu_r',
 'Redor',
 'Redor_r',
 'Reds',
 'Reds_r',
 'Sunset',
 'Sunset_r',
 'Sunsetdark',
 'Sunsetdark_r',
 'Teal',
 'Teal_r',
 'Tealgrn',
 'Tealgrn_r',
 'Turbo',
 'Turbo_r',
 'Viridis',
 'Viridis_r',
 'YlGn',
 'YlGnBu',
 'YlGnBu_r',
 'YlGn_r',
 'YlOrBr',
 'YlOrBr_r',
 'YlOrRd',
 'YlOrRd_r',
 '__all__',
 '__builtins__',
 '__cached__',
 '__doc__',
 '__file__',
 '__loader__',
 '__name__',
 '__package__',
 '__spec__',
 '_cols',
 '_contents',
 '_k',
 '_swatches',
 '_swatches_continuous',
 'algae',
 'algae_r',
 'amp',
 'amp_r',
 'deep',
 'deep_r',
 'dense',
 'dense_r',
 'gray',
 'gray_r',
 'haline',
 'haline_r',
 'ice',
 'ice_r',
 'matter',
 'matter_r',
 'solar',
 'solar_r',
 'speed',
 'speed_r',
 'swatches',
 'swatches_continuous',
 'tempo',
 'tempo_r',
 'thermal',
 'thermal_r',
 'turbid',
 'turbid_r']